University of Cambridge > Talks.cam > Machine Learning @ CUED > Machine Learning and Order Book Dynamics

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

Machine Learning and Order Book Dynamics

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Zoubin Ghahramani.

Standard price-based techniques for predicting future movements of financial assets have low performance over short predictive horizons. Information relating to the interaction of buyers and sellers on exchanges has greater prognostic ability over these time scales. With this in mind, we use the volumes on a EURUSD limit order book to construct simple features. We then take traditional models of market microstructure and incorporate them into the machine learning framework using Fisher kernels. These Fisher kernels are combined with kernels constructed from the simple volume-based features and price-based indicators using Multiple Kernel Learning. Outperformance relative to a benchmark is found for subsets of these kernels.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Clare Hall America Week Fitzwilliam Museum Cambridge Assessment Network These Young Minds Hearing Group Meetings Psychology and Religion Research Group (PRRG)

Other talks

The spin evolution of supermassive black holes Reconciling centennial-scale climate variation during the last millennium in reconstructions and simulations The Most Influential Living Philosopher? Reading and Panel Discussion with Emilia Smechowski CANCELLED: The Loxbridge Triangle: Integrating the East-West Arch into the London Mega-region 100 Problems around Scalar Curvature The Gopakumar-Vafa conjecture for symplectic manifolds Molecular mechanisms of cardiomyopathies in patients with severe non-ischemic heart failure The Rise of Augmented Intelligence in Edge Networks Lunchtime Talk: Helen's Bedroom TODAY Adrian Seminar: "Synaptic plasticity and memory"
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity